What Are AI Chips?

2023-06-04

00:00 / 00:00
复读宝 RABC v8.0beta 复读机按钮使用说明
播放/暂停
停止
播放时:倒退3秒/复读时:回退AB段
播放时:快进3秒/复读时:前进AB段
拖动:改变速度/点击:恢复正常速度1.0
拖动改变复读暂停时间
点击:复读最近5秒/拖动:改变复读次数
设置A点
设置B点
取消复读并清除AB点
播放一行
停止播放
后退一行
前进一行
复读一行
复读多行
变速复读一行
变速复读多行
LRC
TXT
大字
小字
滚动
全页
1
  • Some kinds of computer chips have gained attention recently because they are used in computers linked to artificial intelligence (AI).
  • 2
  • Some experts describe AI chips as similar to graphics chips that speed up complex video games.
  • 3
  • Makers of AI chips say they are designed for AI systems like ChatGPT and will make them faster and less costly.
  • 4
  • The sudden interest in such chips is happening during what some experts call an AI revolution that could change the technology industry.
  • 5
  • Nvidia, led by Jensen Huang, is a maker of graphics chips.
  • 6
  • The company is based in Santa Clara, California.
  • 7
  • Nvidia also is a designer of AI chips.
  • 8
  • Stock shares of the company increased in value by 25 percent last Thursday after company officials predicted a large increase in income.
  • 9
  • The company's stock was briefly valued at more than $1 trillion recently.
  • 10
  • Hanna Dohmen is a researcher with the Center for Security and Emerging Technology in Washington, D.C.
  • 11
  • She said: "There really isn't a completely agreed upon definition of AI chips."
  • 12
  • The term is used to talk about computing equipment that is specialized to deal with AI workloads.
  • 13
  • For example, AI chips are used in "training" AI systems to work out difficult problems.
  • 14
  • Three businessmen founded Nvidia in 1993 to expand the abilities of graphics on computers.
  • 15
  • Within a few years, the company had developed a new chip called a graphics processing unit, or GPU.
  • 16
  • GPUs speed up video games by performing several graphics jobs at the same time.
  • 17
  • The method is known as parallel processing.
  • 18
  • It would be important in the development of both games and AI.
  • 19
  • Two students from the University of Toronto used a GPU-based network to win a 2012 AI competition called ImageNet.
  • 20
  • The network, known as a neural network, could identify photo images at much lower error rates than competitors.
  • 21
  • The award began an interest in AI-related parallel processing.
  • 22
  • And it created new business for Nvidia and its competitors while providing researchers powerful tools for exploring AI development.
  • 23
  • Eleven years after that ImageNet competition, Nvidia is the main supplier of chips for building and updating AI systems.
  • 24
  • One of its recent products, the H100 GPU, has 80 billion transistors.
  • 25
  • That is reportedly about 13 million more than Apple's latest top processor used in its MacBook Pro computers.
  • 26
  • However, this technology is costly. One online seller lists the H100 for $30,000.
  • 27
  • Nvidia does not make these GPU chips itself.
  • 28
  • The company depends on manufacturers such as Taiwan Semiconductor Manufacturing and South Korea's Samsung Electronics.
  • 29
  • Some of the biggest buyers for AI chips are cloud-computing services.
  • 30
  • Technology companies, like Amazon and Microsoft, use these chips for cloud computing.
  • 31
  • These companies permit buyers to pay for temporary computing power to do AI jobs.
  • 32
  • Other companies then can use AI systems without a big investment in buildings and equipment.
  • 33
  • And the cloud-computer services include other tools for drug discovery or helping to oversee customers.
  • 34
  • Parallel processing has many uses outside of AI.
  • 35
  • A few years ago, for example, Nvidia graphics cards were in short supply because cryptocurrency miners had bought most of them.
  • 36
  • A cryptocurrency is a digital form of money that is not overseen or controlled by a government.
  • 37
  • Cryptocurrency miners set up banks of computers to solve mathematical problems for cryptocurrency rewards.
  • 38
  • That problem went away as the cryptocurrency market collapsed in early 2022.
  • 39
  • Researchers say Nvidia will face more competition.
  • 40
  • One possible competitor is Advanced Micro Devices (AMD), which already competes with Nvidia in the market for computer graphics chips.
  • 41
  • AMD has recently taken steps to build its own lineup of AI chips.
  • 42
  • I'm Gregory Stachel.
  • 1
  • Some kinds of computer chips have gained attention recently because they are used in computers linked to artificial intelligence (AI).
  • 2
  • Some experts describe AI chips as similar to graphics chips that speed up complex video games. Makers of AI chips say they are designed for AI systems like ChatGPT and will make them faster and less costly.
  • 3
  • The sudden interest in such chips is happening during what some experts call an AI revolution that could change the technology industry.
  • 4
  • Nvidia, led by Jensen Huang, is a maker of graphics chips. The company is based in Santa Clara, California. Nvidia also is a designer of AI chips. Stock shares of the company increased in value by 25 percent last Thursday after company officials predicted a large increase in income. The company's stock was briefly valued at more than $1 trillion recently.
  • 5
  • What are AI chips?
  • 6
  • Hanna Dohmen is a researcher with the Center for Security and Emerging Technology in Washington, D.C. She said: "There really isn't a completely agreed upon definition of AI chips."
  • 7
  • The term is used to talk about computing equipment that is specialized to deal with AI workloads. For example, AI chips are used in "training" AI systems to work out difficult problems.
  • 8
  • Coming from video games
  • 9
  • Three businessmen founded Nvidia in 1993 to expand the abilities of graphics on computers. Within a few years, the company had developed a new chip called a graphics processing unit, or GPU. GPUs speed up video games by performing several graphics jobs at the same time.
  • 10
  • The method is known as parallel processing. It would be important in the development of both games and AI.
  • 11
  • Two students from the University of Toronto used a GPU-based network to win a 2012 AI competition called ImageNet. The network, known as a neural network, could identify photo images at much lower error rates than competitors.
  • 12
  • The award began an interest in AI-related parallel processing. And it created new business for Nvidia and its competitors while providing researchers powerful tools for exploring AI development.
  • 13
  • Modern AI chips
  • 14
  • Eleven years after that ImageNet competition, Nvidia is the main supplier of chips for building and updating AI systems. One of its recent products, the H100 GPU, has 80 billion transistors. That is reportedly about 13 million more than Apple's latest top processor used in its MacBook Pro computers. However, this technology is costly. One online seller lists the H100 for $30,000.
  • 15
  • Nvidia does not make these GPU chips itself. The company depends on manufacturers such as Taiwan Semiconductor Manufacturing and South Korea's Samsung Electronics.
  • 16
  • Some of the biggest buyers for AI chips are cloud-computing services. Technology companies, like Amazon and Microsoft, use these chips for cloud computing.
  • 17
  • These companies permit buyers to pay for temporary computing power to do AI jobs. Other companies then can use AI systems without a big investment in buildings and equipment. And the cloud-computer services include other tools for drug discovery or helping to oversee customers.
  • 18
  • Other uses and competition
  • 19
  • Parallel processing has many uses outside of AI. A few years ago, for example, Nvidia graphics cards were in short supply because cryptocurrency miners had bought most of them. A cryptocurrency is a digital form of money that is not overseen or controlled by a government.
  • 20
  • Cryptocurrency miners set up banks of computers to solve mathematical problems for cryptocurrency rewards. That problem went away as the cryptocurrency market collapsed in early 2022.
  • 21
  • Researchers say Nvidia will face more competition. One possible competitor is Advanced Micro Devices (AMD), which already competes with Nvidia in the market for computer graphics chips. AMD has recently taken steps to build its own lineup of AI chips.
  • 22
  • I'm Gregory Stachel.
  • 23
  • David Hamilton reported this story for The Associated Press. Gregory Stachel adapted it for VOA Learning English.
  • 24
  • _____________________________________________________________________
  • 25
  • Words in This Story
  • 26
  • computer chip - n. a very small piece of silicon in a computer or electronic device that contains many electronic circuits and can be used to perform work or store memory
  • 27
  • graphics - n. pictures or images on the screen of a computer or television
  • 28
  • update - v. to make (something) more modern
  • 29
  • transistors - n. a small device that is used to control the flow of electricity in radios or computers
  • 30
  • processor - n. the device in a computer that controls the work that the computer does
  • 31
  • cryptocurrency - n. a kind of money not linked to a country or government that exists only online using digital methods to ensure that it is not stolen or falsified
  • 32
  • _____________________________________________________________________
  • 33
  • What do you think of this story?
  • 34
  • We want to hear from you. We have a new comment system. Here is how it works:
  • 35
  • Each time you return to comment on the Learning English site, you can use your account and see your comments and replies to them. Our comment policy is here.